Upload eval_results/AI-MO/deepseek-math-7b-rl-sft/aimo_v01.13/aimo_kaggle_medium_mmos/results_2024-05-24T10-07-11.135359.json with huggingface_hub
Browse files
eval_results/AI-MO/deepseek-math-7b-rl-sft/aimo_v01.13/aimo_kaggle_medium_mmos/results_2024-05-24T10-07-11.135359.json
ADDED
@@ -0,0 +1,91 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"config_general": {
|
3 |
+
"lighteval_sha": "?",
|
4 |
+
"num_fewshot_seeds": 1,
|
5 |
+
"override_batch_size": 4,
|
6 |
+
"max_samples": null,
|
7 |
+
"job_id": "",
|
8 |
+
"start_time": 1251998.579556463,
|
9 |
+
"end_time": 1252318.380801528,
|
10 |
+
"total_evaluation_time_secondes": "319.8012450649403",
|
11 |
+
"model_name": "AI-MO/deepseek-math-7b-rl-sft",
|
12 |
+
"model_sha": "f2387bf0ced9308beb238e535b4d8334e7487ab2",
|
13 |
+
"model_dtype": "torch.bfloat16",
|
14 |
+
"model_size": "12.93 GB",
|
15 |
+
"config": null
|
16 |
+
},
|
17 |
+
"results": {
|
18 |
+
"custom|aimo_kaggle_medium_mmos:v0|0": {
|
19 |
+
"qem": 0.0,
|
20 |
+
"qem_stderr": 0.0
|
21 |
+
},
|
22 |
+
"all": {
|
23 |
+
"qem": 0.0,
|
24 |
+
"qem_stderr": 0.0
|
25 |
+
}
|
26 |
+
},
|
27 |
+
"versions": {
|
28 |
+
"custom|aimo_kaggle_medium_mmos:v0|0": 0
|
29 |
+
},
|
30 |
+
"config_tasks": {
|
31 |
+
"custom|aimo_kaggle_medium_mmos:v0": {
|
32 |
+
"name": "aimo_kaggle_medium_mmos:v0",
|
33 |
+
"prompt_function": "mmos_medium_prompt_fn",
|
34 |
+
"hf_repo": "AI-MO/kaggle-validation-set-medium",
|
35 |
+
"hf_subset": "v0",
|
36 |
+
"metric": [
|
37 |
+
"quasi_exact_match_code"
|
38 |
+
],
|
39 |
+
"hf_avail_splits": [
|
40 |
+
"train"
|
41 |
+
],
|
42 |
+
"evaluation_splits": [
|
43 |
+
"train"
|
44 |
+
],
|
45 |
+
"few_shots_split": null,
|
46 |
+
"few_shots_select": null,
|
47 |
+
"generation_size": 2048,
|
48 |
+
"stop_sequence": null,
|
49 |
+
"output_regex": null,
|
50 |
+
"num_samples": null,
|
51 |
+
"frozen": false,
|
52 |
+
"suite": [
|
53 |
+
"custom"
|
54 |
+
],
|
55 |
+
"original_num_docs": 40,
|
56 |
+
"effective_num_docs": 40,
|
57 |
+
"trust_dataset": null,
|
58 |
+
"must_remove_duplicate_docs": null,
|
59 |
+
"version": 0
|
60 |
+
}
|
61 |
+
},
|
62 |
+
"summary_tasks": {
|
63 |
+
"custom|aimo_kaggle_medium_mmos:v0|0": {
|
64 |
+
"hashes": {
|
65 |
+
"hash_examples": "3401efda8b0cbcb5",
|
66 |
+
"hash_full_prompts": "9553e2c8c7c87406",
|
67 |
+
"hash_input_tokens": "4f9c9b13fc9c2736",
|
68 |
+
"hash_cont_tokens": "cb917267759cd0c9"
|
69 |
+
},
|
70 |
+
"truncated": 40,
|
71 |
+
"non_truncated": 0,
|
72 |
+
"padded": 31,
|
73 |
+
"non_padded": 9,
|
74 |
+
"effective_few_shots": 0.0,
|
75 |
+
"num_truncated_few_shots": 0
|
76 |
+
}
|
77 |
+
},
|
78 |
+
"summary_general": {
|
79 |
+
"hashes": {
|
80 |
+
"hash_examples": "4c81d27cfdb9d737",
|
81 |
+
"hash_full_prompts": "466bf00fd3e3d325",
|
82 |
+
"hash_input_tokens": "f3be8baebf6e5c0d",
|
83 |
+
"hash_cont_tokens": "b39be9d73f59030c"
|
84 |
+
},
|
85 |
+
"truncated": 40,
|
86 |
+
"non_truncated": 0,
|
87 |
+
"padded": 31,
|
88 |
+
"non_padded": 9,
|
89 |
+
"num_truncated_few_shots": 0
|
90 |
+
}
|
91 |
+
}
|